Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/138436
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hausler, S. | - |
dc.contributor.author | Xu, M. | - |
dc.contributor.author | Garg, S. | - |
dc.contributor.author | Chakravarty, P. | - |
dc.contributor.author | Shrivastava, S. | - |
dc.contributor.author | Vora, A. | - |
dc.contributor.author | Milford, M. | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | IEEE Robotics and Automation Letters, 2022; 7(4):10112-10119 | - |
dc.identifier.issn | 2377-3766 | - |
dc.identifier.issn | 2377-3766 | - |
dc.identifier.uri | https://hdl.handle.net/2440/138436 | - |
dc.description.abstract | 6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map. Current techniques use hierarchical pipelines and learned 2D feature extractors to improve scalability and increase performance. However, despite gains in typical recall@0.25mtype metrics, these systems still have limited utility for real-world applications like autonomous vehicles because of their worst areas of performance - the locations where they provide insufficient recall at a certain required error tolerance. Here we investigate the utility of using place specific configurations, where a map is segmented into a number of places, each with its own configuration for modulating the pose estimation step, in this case selecting a camera within a multi-camera system. On the Ford AV benchmark dataset, we demonstrate substantially improved worst-case localization performance compared to using off-the-shelf pipelines - minimizing the percentage of the dataset which has low recall at a certain error tolerance, as well as improved overall localization performance. Our proposed approach is particularly applicable to the crowdsharingmodel of autonomous vehicle deployment, where a fleet of AVs are regularly traversing a known route. | - |
dc.description.statementofresponsibility | Stephen Hausler, Ming Xu, Sourav Garg, Punarjay Chakravarty, Shubham Shrivastava, Ankit Vora, and Michael Milford | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.rights | © 2022 IEEE. | - |
dc.source.uri | http://dx.doi.org/10.1109/lra.2022.3191174 | - |
dc.subject | Autonomous vehicle navigation; deep learning methods; localization; multi camera system | - |
dc.title | Improving Worst Case Visual Localization Coverage via Place-Specific Sub-Selection in Multi-Camera Systems | - |
dc.type | Journal article | - |
dc.identifier.doi | 10.1109/LRA.2022.3191174 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/FL210100156 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Garg, S. [0000-0001-6068-3307] | - |
Appears in Collections: | Australian Institute for Machine Learning publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.